phi3:3.8b
OLLAMA GGUFphi3 · 3.8B · Q4_0
Mar 2, 2026 · Apple M4
liquid/lfm2-24b-a2b
LM-STUDIO MLXlfm2_moe · 24B · 4bit
Apr 1, 2026 · Apple M4
Global Score
64 vs 74
Hardware Fit
100 vs 84
Quality Score
48 vs 69
Hardware
phi3:3.8b liquid/lfm2-24b-a2b
MachineMacBook AirMac mini
CPUApple M4Apple M4
Cores1010
RAM32 GB24 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
phi3:3.8b liquid/lfm2-24b-a2b
Tokens/sec42.051.8
First chunkN/A10 ms
TTFT142 ms503 ms
Load time1.1 sN/A
Memory usage16.0 GB17.5 GB
Memory %50%73%
HW Fit Score Breakdown
phi3:3.8b
Speed
40/50
TTFT
30/20
Memory
30/30
liquid/lfm2-24b-a2b
Speed
50/50
TTFT
20/20
Memory
14/30
Quality
phi3:3.8b
Reasoning
12/20
Coding
3/20
Instruction
11/20
Structured
10/15
Math
5/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Adequate
liquid/lfm2-24b-a2b
Reasoning
11/20
Coding
12/20
Instruction
16/20
Structured
13/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest